Does Sisense Intelligence have any plans for support for custom LLM endpoints. Currently you are limited to the models available in Azure Openai, however there are a lot of great options available in Azure Hub from Huggingface for example, that is a lot cheaper and faster but is not available in Azure Openai and cannot be linked.
Any ideas or feedback would be greatly appreciated!
Hi francoisvv​,
Thank you for reaching out. I have moved this post over to our new Sisense Intelligence group. You should get an answer soon!
We have plans to support additional providers and llms beyond azure open ai.
There are limitations to support any llm type due to: (a) not all llms perform well on our tasks and you may experience an unexpected or explainable drop in performance, and (b) not all expose functions that we rely on like structured output.
Dear Yael, Thanks a lot for your response and it is good to know that you are working on additional providers! We have seen that within Azure, there are amazing models that will surely benefit any type of industry that want to use this feature, and adding Azure Foundry endpoints in addition to Azure OpenAI can be very beneficial. You can refer to the following which I found very useful. https://learn.microsoft.com/en-us/azure/ai-foundry/what-is-azure-ai-foundry
